© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14332
    Prev
    Next
    INDEX
    Explanations

    URL encoding, special characters, code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     before
    -1.55
     when
    -1.48
     what
    -1.46
     these
    -1.30
     those
    -1.30
     despite
    -1.24
     using
    -1.24
    Despite
    -1.23
     some
    -1.23
     found
    -1.23
    POSITIVE LOGITS
     magnificent
    1.63
     dreary
    1.59
     idiotic
    1.57
     intric
    1.54
     wonderfully
    1.49
     masterful
    1.48
     joyful
    1.47
     wondrous
    1.43
     deliciously
    1.41
     serene
    1.41
    Activations Density 0.010%

    No Known Activations